© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35592
    Prev
    Next
    INDEX
    Explanations

    comparisons of conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (er
    -0.09
    /tty
    -0.08
    è°Ľ
    -0.08
    locale
    -0.07
    çºŃ
    -0.07
    зна
    -0.07
     sidel
    -0.07
     ogÅĤoszen
    -0.07
    -être
    -0.07
    æł©
    -0.07
    POSITIVE LOGITS
    eenth
    0.11
    /../
    0.10
    lessly
    0.10
    OfWork
    0.10
    ãĤĩãģĨ
    0.10
    è°¥
    0.09
    åij
    0.09
    usan
    0.09
    éĩĩ访æŶ
    0.08
    èĩ¾
    0.08
    Activations Density 20.612%

    No Known Activations